Advanced search
1 file | 835.86 KB

Real-time vehicle matching for multi-camera tunnel surveillance

Author
Organization
Abstract
Tracking multiple vehicles with multiple cameras is a challenging problem of great importance in tunnel surveillance. One of the main challenges is accurate vehicle matching across the cameras with non-overlapping fields of view. Since systems dedicated to this task can contain hundreds of cameras which observe dozens of vehicles each, for a real-time performance computational efficiency is essential. In this paper, we propose a low complexity, yet highly accurate method for vehicle matching using vehicle signatures composed of Radon transform like projection profiles of the vehicle image. The proposed signatures can be calculated by a simple scan-line algorithm, by the camera software itself and transmitted to the central server or to the other cameras in a smart camera environment. The amount of data is drastically reduced compared to the whole image, which relaxes the data link capacity requirements. Experiments on real vehicle images, extracted from video sequences recorded in a tunnel by two distant security cameras, validate our approach.
Keywords
tunnel surveillance, traffic monitoring, feature extraction, Object recognition, FEATURES

Downloads

  • SPIE manuscriptFinal.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 835.86 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Jelača, Vedran, Jorge Niño Castañeda, Andres Frias Velazquez, Aleksandra Pizurica, and Wilfried Philips. 2011. “Real-time Vehicle Matching for Multi-camera Tunnel Surveillance.” In Proceedings of SPIE, the Society of Photo-Optical Instrumentation Engineers, ed. Nasser Kehtarnavaz and Matthias F Carlsohn. Vol. 7871. Bellinghan, WA, USA: SPIE, the Society of Photo-Optical Instrumentation Engineers.
APA
Jelača, V., Niño Castañeda, J., Frias Velazquez, A., Pizurica, A., & Philips, W. (2011). Real-time vehicle matching for multi-camera tunnel surveillance. In N. Kehtarnavaz & M. F. Carlsohn (Eds.), Proceedings of SPIE, the Society of Photo-Optical Instrumentation Engineers (Vol. 7871). Presented at the Real-Time Image and Video Processing 2011, Bellinghan, WA, USA: SPIE, the Society of Photo-Optical Instrumentation Engineers.
Vancouver
1.
Jelača V, Niño Castañeda J, Frias Velazquez A, Pizurica A, Philips W. Real-time vehicle matching for multi-camera tunnel surveillance. In: Kehtarnavaz N, Carlsohn MF, editors. Proceedings of SPIE, the Society of Photo-Optical Instrumentation Engineers. Bellinghan, WA, USA: SPIE, the Society of Photo-Optical Instrumentation Engineers; 2011.
MLA
Jelača, Vedran, Jorge Niño Castañeda, Andres Frias Velazquez, et al. “Real-time Vehicle Matching for Multi-camera Tunnel Surveillance.” Proceedings of SPIE, the Society of Photo-Optical Instrumentation Engineers. Ed. Nasser Kehtarnavaz & Matthias F Carlsohn. Vol. 7871. Bellinghan, WA, USA: SPIE, the Society of Photo-Optical Instrumentation Engineers, 2011. Print.
@inproceedings{1234711,
  abstract     = {Tracking multiple vehicles with multiple cameras is a challenging problem of great importance in tunnel surveillance. One of the main challenges is accurate vehicle matching across the cameras with non-overlapping fields of view. Since systems dedicated to this task can contain hundreds of cameras which observe dozens of vehicles each, for a real-time performance computational efficiency is essential. In this paper, we propose a low complexity, yet highly accurate method for vehicle matching using vehicle signatures composed of Radon transform like projection profiles of the vehicle image. The proposed signatures can be calculated by a simple scan-line algorithm, by the camera software itself and transmitted to the central server or to the other cameras in a smart camera environment. The amount of data is drastically reduced compared to the whole image, which relaxes the data link capacity requirements. Experiments on real vehicle images, extracted from video sequences recorded in a tunnel by two distant security cameras, validate our approach.},
  articleno    = {78710R},
  author       = {Jela\v{c}a, Vedran and Ni{\~n}o Casta{\~n}eda, Jorge and Frias Velazquez, Andres and Pizurica, Aleksandra and Philips, Wilfried},
  booktitle    = {Proceedings of SPIE, the Society of Photo-Optical Instrumentation Engineers},
  editor       = {Kehtarnavaz, Nasser and Carlsohn, Matthias F},
  isbn         = {9780819484086},
  issn         = {0277-786X},
  keyword      = {tunnel surveillance,traffic monitoring,feature extraction,Object recognition,FEATURES},
  language     = {eng},
  location     = {San Francisco, CA, USA},
  pages        = {8},
  publisher    = {SPIE, the Society of Photo-Optical Instrumentation Engineers},
  title        = {Real-time vehicle matching for multi-camera tunnel surveillance},
  url          = {http://dx.doi.org/10.1117/12.876671},
  volume       = {7871},
  year         = {2011},
}

Altmetric
View in Altmetric
Web of Science
Times cited: